© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13607
    Prev
    Next
    INDEX
    Explanations

    years mentioned as integers in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the year 2016

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onds
    -0.62
    cephal
    -0.58
     clipping
    -0.57
    hed
    -0.57
    irez
    -0.57
     cumbers
    -0.57
    peria
    -0.56
    ificate
    -0.55
     overc
    -0.55
     rapport
    -0.55
    POSITIVE LOGITS
    20439
    1.11
    âĢ²
    0.89
     onwards
    0.85
    âĢ³
    0.80
    -'
    0.73
    bleacher
    0.72
    å¹
    0.70
    ensis
    0.68
     onward
    0.67
     Olympics
    0.66
    Activations Density 0.084%

    No Known Activations